6 papers
Personalizing Large Language Model Agents with Small Policy Models
Dian Jin, Zhi Zhang, Huichao Li +3
Large language model (LLM) agents can retrieve memory, call tools, ask clarifying questions, and vary response style, yet adapting these execution decisions to an individual user r…
Unlearning What Matters: Token-Level Attribution for Precise Language Model Unlearning
Jiawei Wu, Doudou Zhou
Machine unlearning has emerged as a critical capability for addressing privacy, safety, and regulatory concerns in large language models (LLMs). Existing methods operate at the seq…
Model-X Change-Point Detection of Conditional Distribution
Zhuofan Dong, Yiwen Huang, Yan Dong +5
The dynamic nature of many real-world systems can lead to temporal outcome model shifts, causing a deterioration in model accuracy and reliability over time. This requires change-p…
RELEAP: Reinforcement-Enhanced Label-Efficient Active Phenotyping for Electronic Health Records
Yang Yang, Kathryn I. Pollak, Bibhas Chakraborty +3
Objective: Electronic health record (EHR) phenotyping often relies on noisy proxy labels, which undermine the reliability of downstream risk prediction. Active learning can reduce…
SIM-Shapley: A Stable and Computationally Efficient Approach to Shapley Value Approximation
Wangxuan Fan, Siqi Li, Doudou Zhou +4
Explainable artificial intelligence (XAI) is essential for trustworthy machine learning (ML), particularly in high-stakes domains such as healthcare and finance. Shapley value (SV)…
Toward Fair Federated Learning under Demographic Disparities and Data Imbalance
Qiming Wu, Siqi Li, Doudou Zhou +1
Ensuring fairness is critical when applying artificial intelligence to high-stakes domains such as healthcare, where predictive models trained on imbalanced and demographically ske…